Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the write, open-world, non-idempotent, non-destructive profile, and the description adds real behavior on top: RunLater sends the request, retries failures, logs every run, and only public http(s) URLs are accepted with private/local addresses refused. It stops short of warning that repeat calls create duplicate schedules (the non-idempotent consequence) or what auth the caller needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: capability and URL restriction first, the mode-selection rule second, execution behavior and return value last. No filler and nothing buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter creation tool with no output schema, the description covers the mode choice, the public-URL restriction, execution/retry/logging behavior, and the shape of the response (id and next run time). Combined with a fully described schema, an agent has what it needs to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds a cross-parameter rule the schema does not encode: exactly one of run_at or cron must be supplied. That is genuine semantic value beyond the field-level descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (schedule an HTTP request to a public URL) plus the two scheduling modes, and the return value is named. It is clearly distinguishable from siblings like run_now or list_schedules, which do not create schedules.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit constraint for choosing between the two modes: 'Pass exactly one of run_at or cron.' It does not, however, tell the agent when to prefer this tool over run_now (immediate execution) or when a schedule already exists via get_schedule/list_schedules.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.